Qualitative vs. Quantitative Data

What is Qualitative Data?

Qualitative data is data that cannot be objectively measured or counted, or data that expresses the subjective and interpretive qualities of something. Many people only know of data in the numerical sense, but don’t realize that nearly every piece of non-numerical information can be collected and analyzed as qualitative data.

Some examples of qualitative data include:

• The classes that students want to take next semester at Queen City High School.
• The background information of typical recruits for the police academy.
• The types of toys that were purchased during the 2020 holiday season.
• Your friend’s account of what happened at the office today.

Read More: What is Qualitative Data?

What is Quantitative Data?

Quantitative data is any set of information that can be quantified and analyzed statistically. It can be discrete numbers, percentages, fractions, and a variety of other numerical types, but quantitative data must be numeric in order to be measured.

Some examples of quantitative data include:

• The number of dancers in the Paris Opera Ballet Company.
• The birth weights of each of your three sons.
• Total revenue generated over a quarter.
• How many times your kids asked to go to the movies this year (if that can be counted).
• The total percent of the world’s population found in China.

Read More: What is Quantitative Data?

Key Differences: Qualitative vs. Quantitative Data

You can easily find both qualitative and quantitative data in many data sets, but the format, collection, and analysis processes for the two vary greatly. A few key differences between qualitative and quantitative data are:

Data Format

Quantitative data consists solely of numerical values, whereas qualitative data can be any type of content, ranging from words and letters to video and audio clips. Qualitative data can include numbers in certain cases, but quantitative data can never include anything other than numbers.

Collection Process

Although certain collection methods can incorporate quantitative and qualitative data, there are still strict limitations to how each type of data is collected. Quantitative data has to be collected through close-ended methods and questions, or methods that will return a quantitative result and no subjective data. This can be anything from a multiple-choice survey question to an analytics dashboard on a CRM. 

With qualitative data collection, you have more freedom to pose open-ended questions, conduct interviews, and use any other methods you think of to generate subjective responses. The most important part of both quantitative and qualitative data collection is posing the right questions to get the type of data you want in response.

Analysis Process

Quantitative data analysis is more straightforward because statistical analysis and other measurements can be applied to that type of data. With qualitative data analysis, you have a wider range of open-ended responses to consider, so strict measurement is not possible in your analysis. To get a better understanding of a qualitative data set’s makeup, you can try grouping responses into categories and/or using concept mapping to identify themes in the data. 

Read More: Data Analytics Infrastructure: Current Trends

Qualitative vs. Quantitative: Can Data Be Both?

Data can potentially be modified to switch from qualitative data to quantitative data, or vice-versa, but a single piece of data cannot be considered both qualitative and quantitative at the same time. There are also many types of qualitative data that get confused with quantitative data specifically. 

Categorical data is one type of qualitative data that looks like it has turned into quantitative data, because the researcher has divided the data into groups and each of the groups and the quantities within them can now be counted. However, categorical data is not considered quantitative data, because the groups are subjectively defined by the researcher and there is still plenty of non-numeric data available to analyze within the data set.

One of the only ways that typically qualitative data can become quantitative data is if you pose your question with something like a Likert scale. The Likert scale involves asking someone a question that would normally be open-ended, but instead asks them to rate their feelings about that question on a numbered scale. Here’s a good example of what this transformation might look like:

• Qualitative Version: How much do you like our company? Please explain in the blank below. 
  • This is an open-ended question that leaves space for an open-ended response.
• Quantitative Version: On a scale from 1 to 10, with 10 being completely satisfied and 1 being completely unsatisfied, how much do you like our company? 
  • This modified question uses the Likert scale to quantify what would usually be a qualitative, open-ended response. Unlike with the qualitative version, you will not have any context beyond the number that the surveyee selects on the scale.

When and How Can You Use Qualitative and Quantitative Data Together?

There are many situations in which you should collect qualitative and quantitative data together, especially in industries where you want to know a lot of information about your current or future customer base. 

Quantitative data gives you the “what,” or the measurable information that indicates current processes and future outcomes. 

Qualitative data gives you the “who,” “why,” and “how” that helps you to contextualize why that information matters and who it might impact. 

Here are just a few examples of how and why you might use the two together:

Customer and Employee Surveys 

Customer and employee surveys work best when you incorporate both qualitative and quantitative questions. Qualitative data gives you more background information about who they are, how they feel, and why they feel the way that they do. Quantitative data allows you to measure the success and satisfaction rates for each member of the surveyed population, based on numerical information like how long they’ve worked with you or bought your products.

Predictive Analytics

Predictive analytics mostly leans on quantitative data to help you predict outcomes, but let’s consider a healthcare company that uses predictive analytics to predict hospitalization rates across their population. 

Quantitative data tells the organization about the number of hospitalizations, new critical health conditions, and successful treatments that have occurred in a given time period, which allows them to assess how they and their patients are doing based on standardized benchmarks. However, healthcare practitioners also need qualitative data like the patient’s name and contact information, their clinician’s name and contact information, and any care notes associated with their medical profile, in order to solve problems and meet their needs on an individual basis.

Marketing and Sales Sourcing in a CRM

In order to close sales with genuine prospects, your marketing and sales teams need a combination of quantitative and qualitative data to assess prospects that are ready to close. Who has visited your conversion page recently and how many times have they visited? If you see that Mary Jane Smith has visited the page 40 times in the past week, that quantitative data shows you that she’s interested, but something is stopping her from converting into a buyer.

This quantitative data about Mary Jane is invaluable, though it doesn’t mean much without the qualitative data: her name is Mary Jane Smith and her email address is mjbuysfromyou@sales.com. With both the quantitative and qualitative data in hand, your marketing and sales team now have the measurable background information and the contact information they need to do targeted outreach on this prospect.

Both quantitative and qualitative data play important roles in our understanding of populations and processes. But it’s important to recognize how they are different and how their individual strengths compensate for the other’s gaps in data analytics.

Learn More: Big Data Analytics vs. IoT Analytics: Expert Tips 

Read Next: Data Governance Best Practices